進階搜尋


   電子論文尚未授權公開,紙本請查館藏目錄
(※如查詢不到或館藏狀況顯示「閉架不公開」,表示該本論文不在書庫,無法取用。)
系統識別號 U0026-1202201411524500
論文名稱(中文) 癲癇腦波訊號之棘波偵測與辨識
論文名稱(英文) A Study on Spike Detection and Classification from Epileptic EEG Data
校院名稱 成功大學
系所名稱(中) 資訊工程學系
系所名稱(英) Institute of Computer Science and Information Engineering
學年度 102
學期 1
出版年 103
研究生(中文) 劉勇均
研究生(英文) Yung-Chun Liu
學號 p78931024
學位類別 博士
語文別 英文
論文頁數 57頁
口試委員 指導教授-孫永年
口試委員-林宙晴
口試委員-鄭國順
口試委員-江青芬
召集委員-柯建全
口試委員-洪明輝
口試委員-陳建中
中文關鍵字 癲癇  慢波  棘波偵測  棘波辨識  非線性能量運算子  經驗模態分解  矩描述子 
英文關鍵字 epilepsy  slow wave  spike detection  spike classification  nonlinear energy operator  empirical mode decomposition  moment descriptor 
學科別分類
中文摘要 準確的自動化棘波偵測對於癲癇腦電圖的臨床評估是很有幫助的。在本篇論文中,我們提出一套二階層式的癲癇棘波偵測方法。第一階層中,我們使用k點式非線性能量運算子(k-point nonlinear energy operator)來偵測出所有可能的棘波候選點。第二階層中,我們使用不同的方法來對前述棘波候選資料進行特徵擷取,並將擷取出的特徵值用於後續的棘波辨識。首先,我們嘗試使用矩描述子(moment descriptor)來進行特徵擷取,除了直接將之用於候選資料外,也將之用於經過經驗模態分解(empirical mode decomposition)的候選資料上。使用矩描述子能得到不錯的棘波辨識結果,然而這個方法卻不能保留對於棘波辨識來說相當重要的形狀資訊。因此,後續我們提出一種新式以棘波模型為基礎的方法來進行特徵擷取。雖然棘波經常伴隨著慢波(slow wave)出現在癲癇腦電圖中,但這項資訊卻沒有被使用在傳統的棘波辨識上。我們新提出的棘波模型考量了慢波訊息,使得此模型不但能適應於單一棘波,也能適應於伴隨著慢波出現的棘波。使用自適應增強分類器(AdaBoost)為工具進行腦波分類測試,我們所提出的棘波模型無論在分辨兩類或分辨三類的問題上,都比傳統棘波模型的表現來得優異。我們的模型不但辨識率較高,更能進一步區別單一棘波與伴隨慢波出現的棘波。因此,我們所提出的系統有較佳的能力可以協助臨床醫師進行例行的腦電圖判讀與癲癇診斷。
英文摘要 Accurate automatic spike detection is highly beneficial to clinical assessment of epileptic electroencephalogram (EEG) data. In this thesis, a new two–stage approach is proposed for epileptic spike detection. First, the k-point nonlinear energy operator (k-NEO) is used to detect all possible spike candidates. Then, different kinds of features are extracted and applied to these candidates for spike classification. Moment descriptors are first applied as the features to describe the EEG candidate data and the empirical mode decomposed candidate data for spike classification. The statistical moments give promising classification results, however, the moment method does not include the shape information which is critical for epileptic spike classification. We subsequently propose a novel spike model-based method for spike classification. Although spikes with slow waves frequently occur in epileptic EEGs, they are not used in conventional spike detection. The newly proposed system accommodates both the single spike and spike with slow wave in the spike model. Using the AdaBoost classifier, the system outperforms the conventional spike model in both two- and three-class EEG classification problems. It not only achieves better accuracy in spike classification but provides new ability to differentiate between spikes and spikes with slow waves. Consequently, the proposed system has better capability for assisting clinical neurologists in routine EEG examinations and epileptic diagnosis.
論文目次 TABLE OF CONTENTS
摘要 I
ABSTRACT II
誌謝 IV
LIST OF TABLES VII
LIST OF FIGURES VIII
Chapter 1 Introduction 1
1.1 Background and Motivation 1
1.2 Related Works 5
1.3 Thesis Overview 7
Chapter 2 EEG Data Acquisition and Candidate Detection 9
2.1 EEG Data Acquisition 9
2.2 Candidate Detection 12
Chapter 3 Feature Extraction and Classification 14
3.1 Feature Extraction via Moment Based Method 15
3.1.1 Empirical Mode Decomposition 15
3.1.2 Moment Descriptors 23
3.1.3 Features Sets for Moment Based Method 23
3.2 Feature Extraction via Spike Model Based Method 24
3.2.1 Feature Point Selection 24
3.2.2 Spike Model Features 28
3.3 Classification 30
3.3.1 AdaBoost Classifier 30
3.3.2 Classifier Training 31
Chapter 4 Results and Discussion 32
4.1 Candidate Detection 32
4.1.1 Detection Results 32
4.1.2 Parameter Setting of L 32
4.2 Two-Class Classification 33
4.2.1 Evaluation of the Two-Class Classification Problem 33
4.2.2 System Performance using Moment Based Feature Sets 34
4.2.3 System Performance using Spike Model Based Feature Sets 35
4.3 Three-Class Classification 36
4.3.1 Evaluation of the Three-Class Classification Problem 36
4.3.2 System Performance using Moment Based Feature Sets 37
4.3.3 System Performance using Spike Model Based Feature Sets 37
4.4 Pseudo-two-class Classification 38
4.4.1 System Performance using Moment Based Feature Sets 38
4.4.2 System Performance using Spike Model Based Feature Sets 39
Chapter 5 Conclusions 41
5.1 Summary 41
5.2 Future Works 42
References 43
Publications 53
Vitae 57

參考文獻 [1] R. P. Schmidt and B. J. Wilder, Epilepsy, FA Davis: Philadelphia, Pennsylvania, page 4, 1968.
[2] N. Acir, I. Oztura, M. Kuntalp, B. Baklan, and C. Guzelis, “Automatic detection of epileptiform events in EEG by a three-stage procedure based on artificial neural networks,” IEEE Trans. Biomed. Eng., vol. 52, pp. 30-40, 2005.
[3] C. C. Pang, A. R. Upton, G. Shine, and M. V. Kamath, “A comparison of algorithms for detection of spikes in the electroencephalogram,” IEEE Trans. Biomed. Eng., vol. 50, pp. 521-526, 2003.
[4] L. G. Kiloh, A. J. McComas, J. W. Osselton, and A. R. M. Upton, Clinical Electroencephalography, 4th ed., Butterworths: London, UK, 1981.
[5] E. Niedermeyer and F. L. D. Silva, Electroencephalography, Basic Principles, Clinical Applications, and Related Fields, 3rd ed., Williams & Wilkins: Baltimore, MD, 1993.
[6] P. Y. Ktonas, “Automated Spike and Sharp Wave (SSW) Detection,” in Methods of Analysis of Brain Electrical and Magnetic Signals (Handbook of Electroencephalography and Clinical Neurophysiology, Rev Series 1), Elsevier: Amsterdam, The Netherlands, pp. 211-241, 1987.
[7] G. E. Chatrian, L. Bergamini, M. Dondey, D. W. Klass, M. Lennox-Buchthal, and I. Petersen, “A glossary of terms most commonly used by clinical electroencephalographers,” Electroencephalogr. Clin. Neurophysiol., vol. 37, pp. 538-548, 1974.
[8] F. A. Gibbs, H. Davis, and W. G. Lennox, “The electroencephalogram in epilepsy and in conditions of impaired consciousness,” Arch. Neurol. Psychiatr., vol. 34, pp. 1133-1148, 1935.
[9] C. P. Panayiotopoulos, “Typical absence seizures and their treatment,” Arch. Dis. Child., vol. 81, no. 4, pp. 351-355, 1999.
[10] C. P. Panayiotopoulos, The Epilepsies: seizures, syndromes and management, Bladon Medical Publishing: Oxford, UK, pp. 271-348, 2005.
[11] E. Sitnikova and G. Van Luijtelaar, “Electroencephalographic characterization of spike‐wave discharges in cortex and thalamus in WAG/Rij rats”, Epilepsia, vol. 48, no. 12, pp. 2296-2311, 2007.
[12] K. J. Staley, A. White, and F. E. Dudek, “Interictal spikes: Harbingers or causes of epilepsy?,” Neuroscience Letters, vol. 497, no. 3, pp. 247-250, 2011.
[13] G. D. Cascino, P. J. Kelly, F. W. Sharbrough, J. F. Hulihan, K. A. Hirschorn, and M. R. Trenerry, “Long-term follow-up of stereotactic lesionectomy in partial epilepsy: predictive factors and electroencephalographic results,” Epilepsia, vol. 33, no. 4, pp. 639-644, 1992.
[14] R. Krendl, S. Lurger, and C. Baumgartner, “Absolute spike frequency predicts surgical outcome in TLE with unilateral hippocampal atrophy”, Neurology, vol. 71, no. 6, pp. 413-418, 2008.
[15] J. W. Miller and J. Gotman, “The meaning of interictal spikes in temporal lobe epilepsy: should we count them?”, Neurology, vol. 71, no. 6, pp. 392-393, 2008.
[16] A. Rosati, Y. Aghakhani, A. Bernasconi, A. Olivier, F. Andermann, J. Gotman, amd F. Dubeau, “Intractable temporal lobe epilepsy with rare spikes is less severe than with frequent spikes,” Neurology, vol. 60, no. 8 , pp. 1290-1295, 2003.
[17] S. B. Wilson and R. Emerson, “Spike detection: A review and comparison of algorithms,” Clin. Neurophysiol., vol. 113, pp. 1873-1881, 2002.
[18] J. J. Halford, “Computerized epileptiform transient detection in the scalp electroencephalogram: Obstacles to progress and the example of computerized ECG interpretation,” Clin. Neurophysiol., vol. 120, pp. 1909-1915, 2009.
[19] P. Y. Ktonas, “Automated Spike and Sharp Wave (SSW) Detection,” in Methods of Analysis of Brain Electrical and Magnetic Signals (Handbook of Electroencephalography and Clinical Neurophysiology, Rev Series 1), Elsevier: Amsterdam, The Netherlands, pp. 211-241, 1987.
[20] R. Sankar and J. Nator, “Automatic computer analysis of transients in EEG,” Comput. Biol. Med., vol. 22, no. 6, pp. 407-442, 1992.
[21] J. R. Stevens, B. L. Lonsbury, and S. L. Goel, “Seizure occurrence and interspike interval: telemetered electroencephalogram studies,” Arch. Neurol., vol. 26, no. 5, pp. 409-419, 1972.
[22] G. Fischer, N. J. I. Mars, and F. H. Lopez da Silva, Pattern recognition of epileptiform transients in the electroencephalogram, Institute of Medical Physics: Da Costakade, Utrecht, The Netherlands, Report 7, 1980.
[23] Z. Ji, T. Sugi, S. Goto, X. Wang, A. Ikeda, T. Nagamine, H. Shibasaki, and M. Nakamura, “An automatic spike detection system based on elimination of false positives using the large-area context in the scalp EEG,” IEEE Trans. Biomed. Eng., vol. 58, pp. 2478-2488, 2011.
[24] D. O. Walter, H. F. Muller, and R. M. Jell, “Semiautomatic quantification of sharpness of EEG phenomenon,” IEEE Trans. Biomed. Eng., vol. 20, no. 1 pp. 53-55, 1973.
[25] P. Y. Ktonas and J. R. Smith, “Quantification of abnormal EEG spike characteristics,” Comput. Biol. Med., vol. 4, pp. 157-163, 1974.
[26] J. Gotman and P. Gloor, “Automatic recognition and quantification of interictal epileptic activity in the human scalp EEG,” Electroencephalogr. Clin. Neurophysiol., vol. 41, pp. 513-529, 1976.
[27] G. Hellmann, “Multifold features determine linear equation for automatic spike detection applying neural nin interictal ECoG,” Clin. Neurophysiol., vol. 110, pp. 887-894, 1999.
[28] A. A. Dingle, R. D. Jones, G. J. Carroll, and W. R. Fright, “A multistage system to detect epileptiform activity in the EEG,” IEEE Trans. Biomed. Eng., vol. 40, pp. 1260-1268, 1993.
[29] C. W. Ko, Y. D. Lin, H. W. Chang, and G. J. Jan, “An EEG spike detection algorithm using ANN with multichannel correlation,” in Proc. 20th Annu. Int. Conf. IEEE Engineering in Med. and Biol. Soc., pp. 2070-2073, 1998.
[30] H. Qu and J. Gotman, “Improvement in seizure detection performance by automatic adaptation to the EEG of each patient,” Electroenceph. Clin. Neurophysiol., vol. 86, pp. 79-87, 1993.
[31] J. R. Glover, N. Raghavan, P. Y. Ktonas, and J. D. Frost, “Context-based automated detection of epileptogenic sharp transients in the EEG: elimination of false positives,” IEEE Trans. Biomed. Eng., vol. 36, no. 5, pp. 519-527, 1989.
[32] J. R. Glover, P. Y. Ktonas, N. Raghavan, J. M. Urunuela, S. S. Velamuri, and E. L. Reilly, “A multichannel signal processor for the detection of epileptogenic sharp transients in the EEG,” IEEE Trans. Biomed. Eng., vol. BME-33, no. 12, pp. 1121-1128, 1986.
[33] J. R. Glover, D. N. Varmazis, and P. Y. Ktonas, “Continued development of a knowledge-based system to detect epileptogenic sharp transients in the EEG,” in Proc. Conf. IEEE Engineering in Medicine and Biology Society, pp. 1374-1375, 1990.
[34] A. A. Dingle, R. D. Jones, G. J. Carroll, W. R. Fright, and I. M. Donaldson, “The use of multichannel information in the detection of epileptiform activity in the EEG,” in Proc. Conf. IEEE Engineering in Medicine and Biology Society, pp. 849-850, 1990.
[35] J. Gotman and L. Y. Wang, “State-dependent spike detection: concepts and preliminary results,” Electroenceph. Clin. Neurophysiol., vol. 79, pp. 11-19, 1991.
[36] T. P. Exarchos, A. T. Tzallas, D. I. Fotiadis, S. Konitsiotis, and S. Giannopoulos, “EEG transient event detection and classification using association rules,” IEEE Trans. Inf. Technol. Biomed., vol. 10, pp. 451-457, 2006.
[37] J. S. Barlow, “EEG transient detection by matched inverse digital filtering,” Electroencephalogr. Clin. Neurophysiol., vol. 48, pp. 246-248, 1980.
[38] T. Pietilä, S. Vapaakoski, U. Nousiainen, A. Värri, H. Frey, V. Häkkinen, and Y. Neuvo, “Evaluation of a computerized system for recognition of epileptic activity during long-term EEG recording,” Electroencephalogr. Clin. Neurophysiol., vol. 90, no. 6, pp. 438-443, 1994.
[39] T. Sugi, M. Nakamura, A. Ikeda, and H. Shibasaki, “Adaptive EEG spike detection: determination of threshold values based on conditional probability,” Front. Med. Biol. Eng., vol. 11, no. 4, pp. 261-277, 2001.
[40] M. Adjouadi, M. Cabrerizo, M. Ayala, D. Sanchez, I. Yaylali, P. Jayakar, and A. Barreto, “A new mathematical approach based on orthogonal operators for the detection of interictal spikes in epileptogenic data,” Biomed. Sci. Instrum., vol. 40, pp. 175-180, 2004.
[41] K. P. Indiradevi, E. Elias, P. S. Sathidevi, N. S. Dinesh, and K. Radhakrishnan, “A multi-level wavelet approach for automatic detection of epileptic spikes in the electroencephalogram,” Comput. Biol. Med., vol. 38, pp. 805-816, 2008.
[42] T. Kalayci and Ö. Özdamar, “Wavelet preprocessing for automated neural network detection of EEG spikes,” IEEE Eng. Med. Biol. Mag., vol. 14, pp. 160-166, 1995.
[43] S. J. Schiff, A. Aldroubi, M. Unser, and S. Sato, “Fast wavelet transformation of EEG,” Electroenceph. Clin. Neurophysiol., vol. 91, pp. 442-455, 1994.
[44] F. Sartorettoa and M. Ermani, “Automatic detection of epileptiform activity by single-level wavelet analysis,” Clin. Neurophysiol., vol. 110, pp. 239-249, 1999.
[45] M. Latka and Z. Was, “Wavelet analysis of epileptic spikes,” Phys. Rev., vol. 67, pp. 1-4, 2003.
[46] L. Senhadji, J. L. Dillenseger, F. Wendling, C. Rocha, and A. Kinie, “Wavelet analysis of EEG for three-dimensional mapping of epileptic events,” Ann. Biomed. Eng., vol. 23, no. 5, pp. 543-552, 1995.
[47] A. T. Tzallas, P. S. Karvelis, C. D. Katsis, D. I. Fotiadis, S. Giannopoulos, and S. Konitsiotis, “A method for classification of transient events in EEG recordings: application to epilepsy diagnosis,” Methods Inf. Med., vol. 45, pp. 610-621, 2006.
[48] I. Güler and E. D. Übeyli, “Adaptive neuro-fuzzy inference system for classification of EEG signals using wavelet coefficients,” J. Neurosci. Methods, vol. 148, pp. 113-121, 2005.
[49] A. J. Gabor and M. Seyal, “Automated interictal EEG spike detection using artificial neural networks,” Electroenceph. Clin. Neurophysiol., vol. 83, pp. 271-280, 1992.
[50] T. Shimada, T. Shiina, and Y. Saito, “Detection of characteristic waves of sleep EEG by neural network analysis,” IEEE Trans. Biomed. Eng., vol. 47, no. 3, pp. 369-379, 2000.
[51] C. W. Ko and H. W. Chung, “Automatic spike detection via an artificial neural network using raw EEG data: effect of data preparation and implications in the limitations of online recognition,” Clin. Neurophysiol., vol. 111, pp. 477-481, 2000.
[52] R. Eberhart, R. Dobbins, and W. R. S. Webber, “Neural network design considerations for EEG spike detection,” in Proc. 15th Northeast Bioeng. Conf., Boston, MA, pp. 97-98, 1989.
[53] W. R. S. Webber, B. Litt, K. Wilson, and R. Lesser, “Practical detection of epileptiform discharges (ED’s) in the EEG using an artificial neural network: a comparison of raw and parameterized data,” Electroenceph. Clin. Neurophysiol., vol. 91, pp. 194-204, 1994.
[54] G. Jando, R. M. Siegel, Z. Horvath, and G. Buzsaki, “Pattern recognition of the electroencephalogram by artificial neural networks,” Electroenceph. Clin. Neurophysiol., vol. 86, no. 2, pp. 100-109, 1993.
[55] N. Pradhan, P. K. Sadasivan, and G. R. Arunodaya, “Detection of seizure activity in EEG by an artificial neural network: a preliminary study,” Comput. Biomed. Res., vol. 29, no. 4, pp. 303-313, 1996.
[56] C. J. James, R. D. Jones, P. J. Bones, and G. J. Carroll, “Detection of epileptiform discharges in the EEG by a hybrid system comprising mimetic, self-organized artificial neural network, and fuzzy logic stages,” Clin. Neurophysiol., vol. 110, pp. 2049-2063, 1999.
[57] A. J. Gabor, “Seizure detection using a self-organizing neural network: validation and comparison with other detection strategies,” Electroenceph. Clin. Neurophysiol., vol. 107, pp. 27-32, 1998.
[58] F. M. C. Besag, M. Mills, F.Wardale, C. M. Andrew, and M. D. Craggs, “The validation of a new ambulatory spike and wave monitor,” Electroenceph. Clin. Neurophysiol., vol. 73, pp. 157-164, 1989.
[59] Ö. Özdamar and T. Kalayci, “Detection of spikes with artificial neural networks using raw EEG,” Comput. Biomed. Res., vol. 31, pp. 122-142, 1998.
[60] M. Adjouadi, D. Sanchez, M. Cabrerizo, M. Ayala, P. Jayakar, I. Yaylali, and A. Barreto, “Interictal spike detection using the Walsh transform,” IEEE Trans. Biomed. Eng., vol. 51, pp. 868-872, 2004.
[61] H. H. Jasper, “The ten-twenty electrode system of the International Federation,” Electroencephalogr Clin Neurophysiol, vol. 10. pp. 371-375, 1958.
[62] P. Maragos, J. F. Kaiser, and T. F. Quatieri, “On amplitude and frequency demodulation using energy operators,” IEEE Trans. Signal Process., vol. 41, pp. 1532-1550, 1993.
[63] J. F. Kaiser, “On a Simple Algorithm to Calculate the ‘Energy’ of a Signal,” in Proceedings of the IEEE International Conference on Acoustics, Speech, Signal Processing, pp. 381-384, Albuquerque, NM, USA, April 1990.
[64] J. H. Choi and T. Kim, “Neural action potential detector using multi-resolution TEO,” Electron. Lett., vol. 38, pp. 541-543, 2002.
[65] N. E. Huang, Z. Shen, S. R. Long, M. C. Wu, H. H. Shih, Q. Zheng, N. C. Yen, C. C. Tung, and H. H. Liu, “The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis,” in Proceedings of the Royal Society of London, pp. 903-995, 1998.
[66] B. Weng, M. Blanco-Velasco, and K. E. Barner, “ECG denoising based on the empirical mode decomposition,” in the 28th IEEE EMBS Annual International Conference, New York, USA, 2006.
[67] D. Rouvre, D. Kouame, F. Tranquart, and L. Pourcelot, “Empirical mode decomposition (EMD) for multi-gate, multi-transducer ultrasound Doppler fetal heart monitoring,” in the fifth IEEE International Symposium on Signal Processing and Information Technology, 2005.
[68] H. Liang, S. L. Bressler, R. Desimone, and P. Fries, “Empirical mode decomposition: a method for analyzing neural data,” Neurocomputing, vol. 65, pp. 801-807, 2005.
[69] X. Li, “Temporal structure of neuronal population oscillations with empirical model decomposition,” Physics Letters A, vol. 356, no. 3, pp. 237-241, 2006.
[70] H. Liang, Q. H. Lin, and J. D. Z. Chen, “Application of the empirical mode decomposition to the analysis of esophageal manometric data in gastroesophageal reflux disease,” IEEE Trans. on Biomed. Eng., vol. 52, no. 10, pp. 1692-1701, 2005.
[71] Z. Wu and N. E. Huang, “Ensemble empirical mode decomposition: a noise-assisted data analysis method,” Advances in Adaptive Data Analysis, vol. 1, no. 1, pp. 1-41, 2009.
[72] N. E. Huang and Z. Wu, “A review on Hilbert-Huang transform: Method and its applications to geophysical studies,” Reviews of Geophysics, vol. 46, no. 2, RG2006, 23 pages, 2008.
[73] A. Papoulis, Probability, Random Variables, and Stochastic Processes, 2nd ed., McGraw-Hill: New York, USA, 1984.
[74] R. C. Gonzalez and R. E. Woods, Digital Image Processing, 3rd ed, Prentice Hall: New Jersey, USA, pp. 659-660, 2008.
[75] Y. Freund and R. E. Schapire, “A decision-theoretic generalization of on-line learning and an application to boosting,” J. Comput. Syst. Sci., vol. 55, pp. 119-139, 1997.
[76] R. O. Duda, P. E. Hart, and D. G. Stork, Pattern Classification, 2nd ed., John Wiley & Sons: New York, NY, USA, pp. 476-480, 2001.
[77] F. Provost and R. Kohavi, “Glossary of terms,” Mach. Learn., vol. 30, pp. 271-274, 1998.
[78] A. J. Gabor, R. R. Leach, and F. U. Dowla, “Automated seizure detection using a self-organizing neural network,” Electroenceph. Clinic. Neurophysiol., vol. 99, pp. 257–266, 1996.
[79] S. B.Wilson, C. A. Turner, R.G. Emerson, and M. L. Scheuer, “Spike detection II: Automatic, perception-based detection and clustering,” Clin. Neurophysiol., vol. 110, pp. 404–411, 1999.
論文全文使用權限
  • 同意授權校內瀏覽/列印電子全文服務,於2024-01-23起公開。


  • 如您有疑問,請聯絡圖書館
    聯絡電話:(06)2757575#65773
    聯絡E-mail:etds@email.ncku.edu.tw